Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd961b0e78417f1e80902a52b4b9a133d9724bddd4f50db6ac185504a1aebd52
+oid sha256:b069e49564c0005f7bbe2a43367dfc02d8802bb1f1fa26d6559e817c9d386fe8
 size 18516456

last-checkpoint/global_step150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1446547c47965fe5fb42fc2dc6cba0b3f684177f54bc90ede2e6c0bf6eec33b6
+size 27700976

last-checkpoint/global_step150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f4cdadcd1a0689ea0eb56cc968cf0f3f4f1b92630801c057257ad495944d17
+size 27700976

last-checkpoint/global_step150/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3b8b6154786b5023ba55e233d1841a8ea8a2b00c93458234af175adaf5c462
+size 27700976

last-checkpoint/global_step150/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8dbf9e3dff643b4b3705606ca84e3d1ce0d8459810435113ff45eab9076964f
+size 27700976

last-checkpoint/global_step150/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51afb36fc1c2aec0fba4506c863e6fe48ccd030417e546fdb5be787623bf217d
+size 411571

last-checkpoint/global_step150/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef1f48c540d39376b091b83db63fe711d0637b141278838504ecf5d1ca4b587
+size 411507

last-checkpoint/global_step150/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d643f77ba9943866620917d0b9caeee7b1de9fe5f3285b6bce15255cef3b9e5
+size 411507

last-checkpoint/global_step150/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f3633915e6bd4b58698e89a33c3f9b98467334d4e69888dc12a2eb89f7e7ca
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step100
+global_step150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+oid sha256:70cc56408014c410353d4dd58ae9b03f4be043f5f800324f66fd8e20e99b840e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+oid sha256:49d1438e98cc9c53a6852464635ce62e9788e61eb3646b73e33813f487c4b6ae
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+oid sha256:4388add9cec90932f8ff0100d27a0574d98e1bad52ff89d44e31967d2b4fbfde
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+oid sha256:a705d6dfaae4f2c1b4b2be6b25a6eb521ffae6fcba21cc1531e97b60037ed079
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e451a9e086b06d7c667be8442b2115f5c088953bade0b625e61f2ce5c7fd404
+oid sha256:c587ef55825cdfdbac47c29c3bd8a2996263c16833a5bd6aaa2fb014bea1e9d1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9077914953231812,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-100",
-  "epoch": 0.05150656708730363,
+  "best_metric": 0.8962129950523376,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-150",
+  "epoch": 0.07725985063095545,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -185,11 +185,100 @@
       "eval_steps_per_second": 0.888,
       "num_input_tokens_seen": 1169664,
       "step": 100
+    },
+    {
+      "epoch": 0.05408189544166881,
+      "grad_norm": 0.412918917979438,
+      "learning_rate": 6.176470588235295e-05,
+      "loss": 0.9159,
+      "num_input_tokens_seen": 1228112,
+      "step": 105
+    },
+    {
+      "epoch": 0.056657223796033995,
+      "grad_norm": 0.34797408069968117,
+      "learning_rate": 6.470588235294118e-05,
+      "loss": 0.91,
+      "num_input_tokens_seen": 1286608,
+      "step": 110
+    },
+    {
+      "epoch": 0.05923255215039917,
+      "grad_norm": 0.27558494796967653,
+      "learning_rate": 6.764705882352942e-05,
+      "loss": 0.9047,
+      "num_input_tokens_seen": 1345072,
+      "step": 115
+    },
+    {
+      "epoch": 0.06180788050476436,
+      "grad_norm": 0.5422134023513459,
+      "learning_rate": 7.058823529411765e-05,
+      "loss": 0.9022,
+      "num_input_tokens_seen": 1403544,
+      "step": 120
+    },
+    {
+      "epoch": 0.06438320885912954,
+      "grad_norm": 0.4452796218739235,
+      "learning_rate": 7.352941176470589e-05,
+      "loss": 0.9081,
+      "num_input_tokens_seen": 1462024,
+      "step": 125
+    },
+    {
+      "epoch": 0.06695853721349472,
+      "grad_norm": 0.5632558160730559,
+      "learning_rate": 7.647058823529411e-05,
+      "loss": 0.8939,
+      "num_input_tokens_seen": 1520528,
+      "step": 130
+    },
+    {
+      "epoch": 0.0695338655678599,
+      "grad_norm": 0.3383115884436812,
+      "learning_rate": 7.941176470588235e-05,
+      "loss": 0.9029,
+      "num_input_tokens_seen": 1579024,
+      "step": 135
+    },
+    {
+      "epoch": 0.07210919392222509,
+      "grad_norm": 0.3506611095466577,
+      "learning_rate": 8.23529411764706e-05,
+      "loss": 0.9014,
+      "num_input_tokens_seen": 1637504,
+      "step": 140
+    },
+    {
+      "epoch": 0.07468452227659027,
+      "grad_norm": 0.6328034405712752,
+      "learning_rate": 8.529411764705883e-05,
+      "loss": 0.9053,
+      "num_input_tokens_seen": 1696024,
+      "step": 145
+    },
+    {
+      "epoch": 0.07725985063095545,
+      "grad_norm": 0.3511657661506363,
+      "learning_rate": 8.823529411764706e-05,
+      "loss": 0.9032,
+      "num_input_tokens_seen": 1754512,
+      "step": 150
+    },
+    {
+      "epoch": 0.07725985063095545,
+      "eval_loss": 0.8962129950523376,
+      "eval_runtime": 17.0673,
+      "eval_samples_per_second": 3.515,
+      "eval_steps_per_second": 0.879,
+      "num_input_tokens_seen": 1754512,
+      "step": 150
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 1169664,
+  "num_input_tokens_seen": 1754512,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -204,7 +293,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 65637304762368.0,
+  "total_flos": 98478685421568.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null